© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 81
    Prev
    Next
    INDEX
    Explanations

    names and designations of football positions and players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Short abbreviations denoting professional positions, roles, or technical classifications, typically appearing after names or as part of formal descriptions.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioned
    -0.07
    .toolbox
    -0.07
    usercontent
    -0.07
    izedName
    -0.07
    urement
    -0.06
    eve
    -0.06
    orer
    -0.06
    isposable
    -0.06
    rig
    -0.06
     mất
    -0.06
    POSITIVE LOGITS
    ëĮĢíĸī
    0.06
    rike
    0.06
    .heap
    0.06
     Kons
    0.06
    ãģ©ãģĨ
    0.06
    allon
    0.06
     onward
    0.06
     usu
    0.06
    óz
    0.06
    QUEST
    0.05
    Activations Density 0.048%

    No Known Activations